CORAL: COntextual Reasoning And Local Planning in A Hierarchical VLM Framework for Underwater Monitoring

• URL: http://arxiv.org/abs/2603.14786v1
• Date: Mon, 16 Mar 2026 03:35:08 GMT
• Title: CORAL: COntextual Reasoning And Local Planning in A Hierarchical VLM Framework for Underwater Monitoring
• Abstract summary: Oyster reefs are critical ecosystem species that sustain biodiversity, filter water, and protect coastlines, yet they continue to decline globally.<n>Regular underwater monitoring to assess reef health is costly, hazardous, and limited when performed by human divers.<n>Existing autonomous underwater vehicles (AUVs) rely on geometry-based navigation that cannot interpret scene semantics.<n>Recent vision-language models (VLMs) enable semantic reasoning for intelligent exploration, but existing VLM-driven systems adopt an end-to-end paradigm.<n>We propose CORAL, a framework that decouples high-level semantic reasoning from low-level reactive control.
• Score: 10.250809787836607
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Oyster reefs are critical ecosystem species that sustain biodiversity, filter water, and protect coastlines, yet they continue to decline globally. Restoring these ecosystems requires regular underwater monitoring to assess reef health, a task that remains costly, hazardous, and limited when performed by human divers. Autonomous underwater vehicles (AUVs) offer a promising alternative, but existing AUVs rely on geometry-based navigation that cannot interpret scene semantics. Recent vision-language models (VLMs) enable semantic reasoning for intelligent exploration, but existing VLM-driven systems adopt an end-to-end paradigm, introducing three key limitations. First, these systems require the VLM to generate every navigation decision, forcing frequent waits for inference. Second, VLMs cannot model robot dynamics, causing collisions in cluttered environments. Third, limited self-correction allows small deviations to accumulate into large path errors. To address these limitations, we propose CORAL, a framework that decouples high-level semantic reasoning from low-level reactive control. The VLM provides high-level exploration guidance by selecting waypoints, while a dynamics-based planner handles low-level collision-free execution. A geometric verification module validates waypoints and triggers replanning when needed. Compared with the previous state-of-the-art, CORAL improves coverage by 14.28% percentage points, or 17.85% relatively, reduces collisions by 100%, and requires 57% fewer VLM calls.

Related papers

• Embodied-Navigator: Point, Think, Memorize, and Align for Efficient Navigation [68.02899606570223]
  We propose TAMP-Nav, a unified framework for efficient embodied navigation.<n>First, we introduce a Pixel-to-3D Action Formulation (Point) that reformulates navigation into 2D visual coordinates.<n>Second, we propose an integrated Selective Reasoning and Anchor-Trajectory Memory mechanism (Think and Memorize)
  arXiv  Detail & Related papers  (2026-08-18T08:37:08Z)
• Hierarchical Topology-Aware Planning and Control of Underwater Vehicle-Manipulator Systems in Confined Environments [2.5199066832791526]
  Poor maneuverability, narrow passages, and uncertain execution may cause the robot to enter unrecoverable regions.<n>We propose MANTA, a three-layer hierarchical planning-and-control framework that couples passage accessibility, manipulation feasibility, and closed-loop execution.<n>MANTA is evaluated in confined UVMS planning and closed-loop tracking experiments.
  arXiv  Detail & Related papers  (2026-08-09T19:22:51Z)
• S-squared-VLA: Decoupling Semantic and Spatial Streams in Vision-Language-Action Models for Autonomous Driving [8.813976817688605]
  Vision-Language Models (VLMs) have demonstrated remarkable potential for high-level reasoning in autonomous driving.<n>VLMs struggle to generate precise, low-level control actions due to mismatch between discrete language tokens and continuous trajectory planning.<n>We propose the S-squared-VLA, which explicitly decouples the semantic and spatial streams in Vision-Language-Action models.
  arXiv  Detail & Related papers  (2026-07-15T15:07:02Z)
• RENEW: Risk- and Energy-Aware Navigation in Dynamic Waterways [10.620311022921205]
  We present RENEW, a global path planner for Autonomous Surface Vehicle (ASV) in dynamic environments with external disturbances.<n>We introduce a unified risk- and energy-aware strategy that ensures safety by dynamically identifying non-navigable regions.<n>Inspired by maritime contingency planning, it employs a best-effort strategy to maintain control under adverse conditions.
  arXiv  Detail & Related papers  (2026-01-23T03:33:52Z)
• Deep Learning-based Robust Autonomous Navigation of Aerial Robots in Dense Forests [7.726773291477927]
  This work presents an improved deep learning-based navigation framework that integrates semantically enhanced depth encoding with neural motion-primitive evaluation for robust flight in cluttered forests.<n>The system is deployed on a custom quadrotor in three boreal forest environments, achieving fully autonomous completion in all flights in moderate and dense clutter, and 12 out of 15 flights in highly dense underbrush.
  arXiv  Detail & Related papers  (2025-12-19T13:19:33Z)
• IndustryNav: Exploring Spatial Reasoning of Embodied Agents in Dynamic Industrial Navigation [56.43007596544299]
  IndustryNav is the first dynamic industrial navigation benchmark for active spatial reasoning.<n>A study of nine state-of-the-art Visual Large Language Models reveals that closed-source models maintain a consistent advantage.
  arXiv  Detail & Related papers  (2025-11-21T16:48:49Z)
• Hybrid DQN-TD3 Reinforcement Learning for Autonomous Navigation in Dynamic Environments [1.241204035960416]
  This paper presents a hierarchical path-planning and control framework that combines a high-level Deep Q-Network (DQN) for discrete sub-goal selection with a low-level Twin Delayed Deep Deterministic Policy Gradient (TD3) controller for continuous actuation.<n>We design a practical reward shaping scheme (direction, distance, obstacle avoidance, action smoothness, collision penalty, time penalty, and progress) together with a LiDAR-based safety gate that prevents unsafe motions.
  arXiv  Detail & Related papers  (2025-10-30T16:12:01Z)
• NOVA: Navigation via Object-Centric Visual Autonomy for High-Speed Target Tracking in Unstructured GPS-Denied Environments [56.35569661650558]
  We introduce NOVA, a fully onboard, object-centric framework that enables robust target tracking and collision-aware navigation.<n>Rather than constructing a global map, NOVA formulates perception, estimation, and control entirely in the target's reference frame.<n>We validate NOVA across challenging real-world scenarios, including urban mazes, forest trails, and repeated transitions through buildings with intermittent GPS loss.
  arXiv  Detail & Related papers  (2025-06-23T14:28:30Z)
• DORAEMON: Decentralized Ontology-aware Reliable Agent with Enhanced Memory Oriented Navigation [55.888688171010365]
  DORAEMON is a cognitive-inspired framework consisting of Ventral and Dorsal Streams that mimics human navigation capabilities.<n>We evaluate DORAEMON on the HM3D, MP3D and GOAT datasets, where it achieves state-of-the-art performance on both success rate (SR) and success weighted by path length (SPL) metrics.
  arXiv  Detail & Related papers  (2025-05-28T04:46:13Z)
• Depth-Constrained ASV Navigation with Deep RL and Limited Sensing [43.785833390490446]
  We propose a reinforcement learning framework for ASV navigation under depth constraints.<n>To enhance environmental awareness, we integrate GP regression into the RL framework.<n>We demonstrate effective sim-to-real transfer, ensuring that trained policies generalize well to real-world aquatic conditions.
  arXiv  Detail & Related papers  (2025-04-25T10:56:56Z)
• Image-Based Relocalization and Alignment for Long-Term Monitoring of Dynamic Underwater Environments [57.59857784298534]
  We propose an integrated pipeline that combines Visual Place Recognition (VPR), feature matching, and image segmentation on video-derived images.<n>This method enables robust identification of revisited areas, estimation of rigid transformations, and downstream analysis of ecosystem changes.
  arXiv  Detail & Related papers  (2025-03-06T05:13:19Z)
• Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection [56.66677293607114]
  We propose Code-as-Monitor (CaM) for both open-set reactive and proactive failure detection.<n>To enhance the accuracy and efficiency of monitoring, we introduce constraint elements that abstract constraint-related entities.<n>Experiments show that CaM achieves a 28.7% higher success rate and reduces execution time by 31.8% under severe disturbances.
  arXiv  Detail & Related papers  (2024-12-05T18:58:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.